Benchmark Almanac

DP-Bench

upstage (enhanced) document parser 96.6 tops its leaderboard
Not in model cards

Document parsers and vision models convert PDFs and scanned pages into structured HTML or Markdown. Output is compared with reference structure.

About 90 likes on Hugging Face.

Made by
Upstage
Released
October 2024
Kind
Documents, charts and text in images
Level
Everyday
Scored
Checked automatically
Answers
Short answer
Tasks
All public
7
Entries on its own leaderboard, 0 models we track

upstage (enhanced) document parser tops the leaderboard with 96.6

Best score per entry from the benchmark's own leaderboard, read on November 12th, 2026. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders.

  1. 96.6 upstage (enhanced) document parser
  2. 96.3 upstage (standard) document parser
  3. 96.0 aws document parser
  4. 91.8 unstructured document parser
  5. 90.5 llamaparse document parser
  6. 87.0 microsoft document parser
  7. 82.2 google document parser
  1. 1 upstage (enhanced) document parser NID layout score 96.6
  2. 2 upstage (standard) document parser NID layout score 96.3
  3. 3 aws document parser NID layout score 96.0
  4. 4 unstructured document parser NID layout score 91.8
  5. 5 llamaparse document parser NID layout score 90.5
  6. 6 microsoft document parser NID layout score 87.0
  7. 7 google document parser NID layout score 82.2

Source: Official DP-Bench leaderboard

#EntryScoreSettingDateSource
1 upstage (enhanced) document parser 96.6 NID layout score Feb 2026 Official leaderboard
2 upstage (standard) document parser 96.3 NID layout score Feb 2026 Official leaderboard
3 aws document parser 96.0 NID layout score Feb 2026 Official leaderboard
4 unstructured document parser 91.8 NID layout score Feb 2026 Official leaderboard
5 llamaparse document parser 90.5 NID layout score Feb 2026 Official leaderboard
6 microsoft document parser 87.0 NID layout score Feb 2026 Official leaderboard
7 google document parser 82.2 NID layout score Feb 2026 Official leaderboard

No lab model card reports it yet

We read the headline results of 522 launch posts from 52 labs, and none of them list this benchmark.

More in Vision

All 281 in Vision
  • MMMU In use 11.5K college-level multimodal questions across 30 subjects. Multiple-choice and open accuracy. GPT-5.1 85.4%
  • MMMU-Pro In use Harder MMMU: college-level multimodal questions with more options and vision-only inputs to remove text shortcuts. GPT-5.6 Sol 84.6%
  • CharXiv In use Chart understanding on real arXiv figures. Reasoning questions require synthesizing information from complex charts. Claude Fable 5 93.5%
  • MATH-Vision (MathVision) In use 3,040 competition math problems with visual context. Answer accuracy. Qwen 3.8 Max 97.7%
  • MMStar In use Models answer 1,500 human-curated image questions that cannot be solved without the image, across 6 core capabilities. Scored by accuracy. Qwen 3.8 Max 85.9%
  • ChartQA In use Models answer human-written and generated questions about chart images that need visual and arithmetic reasoning. Scored by relaxed accuracy with a 5 percent numeric tolerance. Command A Vision 90.9%